Target-Aware Neural Architecture Search and Deployment for Keyword Spotting

Busia P.;Deriu G.;Raffo L.;Meloni P.
2022-01-01

Abstract

Keyword spotting (KWS) utilities have become increasingly popular on a wide range of mobile and home devices, representing a prolific application field for Convolutional Neural Networks (CNNs), which are commonly exploited to perform keyword classification. Addressing the challenges of targeting such resource-constrained platforms, requires a careful definition of the CNN architecture and the overall system implementation. These reasons have led to a growing need for design and optimization flows, able to intrinsically take into account the system's performance when ported on the target platform. In this work, we present a design methodology based on Neural Architecture Search, exploited to combine the exploration of the optimal network topology, the audio pre-processing scheme, and the data quantization policy. The proposed design flow includes target-awareness in the exploration loop, comparing the different design alternatives according to a model-based pre-evaluation of metrics like execution latency, memory footprint, and energy consumption, evaluated considering the application's execution on the target processing platform. We have tested our design flow to obtain target-specific CNNs for a resource-constrained commercial platform, the ST SensorTile. Considering two different application scenarios, enabling the comparison with the state-of-the-art of efficient CNN-based models for KWS, we have obtained up to a 1.8% accuracy improvement and a 40% footprint reduction in the most favorable case.
2022
Keyword spotting; neural networks; neural architecture search
Files in This Item:
File Size Format  
Target-Aware_Neural_Architecture_Search_and_Deployment_for_Keyword_Spotting.pdf

open access

Description: articolo online
Type: versione editoriale
Size 1.84 MB
Format Adobe PDF
1.84 MB Adobe PDF View/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Questionnaire and social

Share on:
Impostazioni cookie